cvs commit: src/sys/i386/isa clock.c

[Bruce Evans]

On Fri, 30 Apr 2004, Mike Silbersack wrote:

> Hm, I just learned something interesting about my clock issue... good
> thing that I was saving dmesgs for warner:
>
> Nov 13, 2003:
> CPU: Mobile Intel(R) Celeron(R) CPU 1.60GHz (1594.98-MHz 686-class CPU)
>
> Apr 10, 2004, with ACPI:
> CPU: Mobile Intel(R) Celeron(R) CPU 1.60GHz (1556.71-MHz 686-class CPU)
>
> Apr 10, 2004, without ACPI:
> CPU: Mobile Intel(R) Celeron(R) CPU 1.60GHz (1575.84-MHz 686-class CPU)
>
> today, without ACPI:
> CPU: Mobile Intel(R) Celeron(R) CPU 1.60GHz (1575.84-MHz 686-class CPU)

The TSC calibration is lower level than the bug fixed in the commit.
It just uses DELAY(1000000) without even adjusting for DELAY()'s
overhead.  Perhaps acpi is working "better" and throttling the cpu
during the calibration, or something is interrupting the calibration.
I hope FreeBSD still has interrupts disabled at that point, but there
may be SMM interrupts especially with acpi.

> I also noticed this today from vmstat -i:
>
> interrupt                          total       rate
> irq0: clk                         746040        986
> irq8: rtc                          95484        126
>
> That should be 1000 & 128, if I'm not mistaken.  Are these all symptoms of
> some timing code during boot messing up?

Depends on the timecounter.  The vmstat -i times are consistent with
using the TSC timecounter after miscalibrating the TSC by a factor of
1556/1575.  Other timecounters don't use boot time calibration by
default (i8254) or at all (acpi).

Bruce